175 citations · 269 across the 10 of their papers we have counts for
14 papers · 1 filter
Measuring Compositional Consistency for Video Question Answering
Mona Gandhi, Mustafa Omer Gul, Eva Prakash +3
Recent video question answering benchmarks indicate that state-of-the-art models struggle to answer compositional questions. However, it remains unclear which types of compositiona…
AGQA 2.0: An Updated Benchmark for Compositional Spatio-Temporal Reasoning
Madeleine Grunde-McLaughlin, Ranjay Krishna, Maneesh Agrawala
Prior benchmarks have analyzed models' answers to questions about videos in order to measure visual compositional reasoning. Action Genome Question Answering (AGQA) is one such ben…
AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning
Madeleine Grunde-McLaughlin, Ranjay Krishna, Maneesh Agrawala
Visual events are a composition of temporal actions involving actors spatially interacting with objects. When developing computer vision models that can reason about compositional…
Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
Jingwei Ji, Ranjay Krishna, Li Fei-Fei +1
Action recognition has typically treated actions and activities as monolithic events that occur in videos. However, there is evidence from Cognitive Science and Neuroscience that p…
Deep Bayesian Active Learning for Multiple Correct Outputs
Khaled Jedoui, Ranjay Krishna, Michael Bernstein +1
Typical active learning strategies are designed for tasks, such as classification, with the assumption that the output space is mutually exclusive. The assumption that these tasks…
Learning Predicates as Functions to Enable Few-shot Scene Graph Prediction
Apoorva Dornadula, Austin Narcomey, Ranjay Krishna +2
Scene graph prediction --- classifying the set of objects and predicates in a visual scene --- requires substantial training data. However, most predicates only occur a handful of…